Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    comments or annotations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code comments starting with /*

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    botella
    -0.53
     Pound
    -0.52
    Authority
    -0.48
    Quo
    -0.48
     Cowell
    -0.46
     tỉ
    -0.46
     Headline
    -0.46
    entr
    -0.46
    downs
    -0.46
     downs
    -0.46
    POSITIVE LOGITS
    /*
    2.09
    /*
    1.88
     /*
    1.56
    (/*
    1.23
    }/*
    1.23
    /*
    1.21
    +/*
    1.12
    /*@
    0.99
    /*"
    0.93
    /*",
    0.85
    Act Density 0.017%

    No Known Activations